2.765

2022影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于多层注意力和消息传递网络的药物相互作用预测方法

饶晓洁 张通 孟献兵 陈俊龙

饶晓洁, 张通, 孟献兵, 陈俊龙. 基于多层注意力和消息传递网络的药物相互作用预测方法. 自动化学报, 2023, 49(12): 2507−2519 doi: 10.16383/j.aas.c220371
引用本文: 饶晓洁, 张通, 孟献兵, 陈俊龙. 基于多层注意力和消息传递网络的药物相互作用预测方法. 自动化学报, 2023, 49(12): 2507−2519 doi: 10.16383/j.aas.c220371
Rao Xiao-Jie, Zhang Tong, Meng Xian-Bing, Chen C. L. Philip. Drug-drug interaction prediction method based on multi-level attention mechanism and message passing neural network. Acta Automatica Sinica, 2023, 49(12): 2507−2519 doi: 10.16383/j.aas.c220371
Citation: Rao Xiao-Jie, Zhang Tong, Meng Xian-Bing, Chen C. L. Philip. Drug-drug interaction prediction method based on multi-level attention mechanism and message passing neural network. Acta Automatica Sinica, 2023, 49(12): 2507−2519 doi: 10.16383/j.aas.c220371

基于多层注意力和消息传递网络的药物相互作用预测方法

doi: 10.16383/j.aas.c220371
基金项目: 国家重点研发计划(2019YFB1703600), 国家自然科学基金 (62006081), 广东省自然科学基金面上项目 (2022A1515011317), 中国博士后科学基金(2020M672630) 资助
详细信息
    作者简介:

    饶晓洁:华南理工大学计算机科学与工程学院硕士研究生. 主要研究方向为机器学习与人工智能在生物医药领域的应用. E-mail: rxj19971214@163.com

    张通:华南理工大学计算机科学与工程学院教授. 2016年获得澳门大学软件工程专业博士学位. 主要研究方向为情感计算, 进化计算, 神经网络和其他机器学习技术及其应用. E-mail: tony@scut.edu.cn

    孟献兵:华南理工大学计算机科学与工程学院助理研究员. 2019年获中南大学博士学位. 主要研究方向为计算智能和人工智能算法及其应用. 本文通信作者. E-mail: axbmeng@gmail.com

    陈俊龙:华南理工大学计算机科学与工程学院教授. 主要研究方向为控制论, 智能系统和计算智能E-mail: philipchen@scut.edu.cn

Drug-drug Interaction Prediction Method Based on Multi-level Attention Mechanism and Message Passing Neural Network

Funds: Supported by National Key Research and Development Program of China (2019YFB1703600), National Natural Science Foundation of China (62006081), Natural Science Foundation of Guangdong Province (2022A1515011317), and China Postdoctoral Science Foundation Project (2020M672630)
More Information
    Author Bio:

    RAO Xiao-Jie Master student at the School of Computer Science and Engineering, South China University of Technology. Her research interest covers application of machine learning and artificial intelligence in the field of biomedicine

    ZHANG Tong Professor at the School of Computer Science and Engineering, South China University of Technology. He received his Ph.D. degree in software engineering from University of Macau in 2016. His research interest covers affective computing, evolutionary computation, neural network, and other machine learning techniques and their applications

    MENG Xian-Bing Assistant research fellow at the School of Computer Science and Engineering, South China University of Technology. He received his Ph.D. degree from Central South University in 2019. His research interest covers computational intelligence and artificial intelligence algorithms and their applications. Corresponding author of this paper

    CHEN C. L. Philip Professor at the School of Computer Science and Engineering, South China University of Technology. His research interest covers cybernetics, intelligent systems, and computational intelligence

  • 摘要: 药物相互作用(Drug-drug interaction, DDI)是指不同药物存在抑制或促进等作用. 现有DDI预测方法往往直接利用药物分子特征表示预测DDI, 而忽略药物分子中不同原子对DDI的影响. 为此, 提出基于多层次注意力机制和消息传递神经网络的DDI预测方法. 该方法将DDI建模为通过学习基于序列表示的药物分子特征实现DDI预测的链接预测问题. 首先, 建立基于注意力机制和消息传递神经网络的原子特征网络, 结合提出的基于分子质心的位置编码, 学习不同原子及其相关联化学键的特征, 构建基于图结构的药物分子特征表示; 然后, 设计基于注意力机制的分子特征网络, 并通过监督和对比损失学习, 实现DDI预测; 最后, 通过实验证明该方法的有效性和优越性.
  • 图  1  模型框架图

    Fig.  1  Framework of the proposed model

    图  2  基于注意力机制的消息传递原子特征网络

    Fig.  2  Framework of the message passing atomic feature network base on attention mechanism

    图  3  药物分子之间注意力分数的可视化

    Fig.  3  Visualization of attention scores between drug molecules

    图  4  位置编码对模型收敛性能的影响

    Fig.  4  The effect of positional encoding on model convergence performance

    图  5  在ZhangDDI数据集上不同$\alpha$和$\beta$取值对模型性能的影响

    Fig.  5  The effects of different $\alpha$ and $\beta$ on model performance on ZhangDDI dataset

    图  6  在ChCh-Miner数据集上不同$\alpha$和$\beta$取值对模型性能的影响

    Fig.  6  The effects of different $\alpha$ and $\beta$ on model performance on ChCh-Miner dataset

    表  1  ZhangDDI数据集上的对比实验结果

    Table  1  Comparison experimental results on ZhangDDI dataset

    模型AUROCAUPRCF1
    NN[24]67.81±0.2552.61±0.2749.84±0.43
    LP-Sub[25]93.39±0.1389.15±0.1379.61±0.16
    LP-SE[25]93.48±0.2589.61±0.1979.83±0.61
    LP-OSE[25]93.50±0.2490.31±0.8280.41±0.51
    MF-Ens[11]95.20±0.1492.51±0.1585.41±0.16
    SSP-MLP[1]92.51±0.1588.51±0.6680.69±0.81
    GCN[26]91.91±0.6288.73±0.8481.61±0.39
    GIN[27]81.45±0.2677.16±0.1664.15±0.16
    Att-auto[12]92.84±0.6190.21±0.1970.96±0.39
    GAT[28]91.49±0.2990.69±0.1080.93±0.25
    SEAL-CI[29]92.93±0.1992.82±0.1784.74±0.17
    NFP-GCN[30]93.22±0.0993.07±0.4685.29±0.38
    MIRACLE[13]98.95±0.1598.17±0.0693.20±0.27
    本文方法99.14±0.0197.97±0.0293.79±0.28
    下载: 导出CSV

    表  2  ChCh-Miner数据集上的对比实验结果

    Table  2  Comparison experimental results on ChCh-Miner dataset

    模型AUROCAUPRCF1
    GCN[26]82.84±0.6184.27±0.6670.54±0.87
    GIN[27]70.32±0.8772.41±0.6365.54±0.97
    GAT[28]85.84±0.2388.14±0.2576.51±0.38
    SEAL-CI[29]90.93±0.1989.38±0.3984.74±0.48
    NFP-GCN[30]92.12±0.0993.07±0.6985.41±0.18
    MIRACLE[13]96.15±0.2995.57±0.1992.26±0.09
    本文方法98.45±0.3199.79±0.0496.51±0.84
    下载: 导出CSV

    表  3  原子特征网络的消融实验结果

    Table  3  Ablation experimental results on atomic feature network

    数据集算法AUROCAUPRCF1
    ZhangDDI无注意力的
    原子网络
    98.70±0.2096.89±0.5090.46±1.18
    本文方法99.14±0.0197.97±0.0293.79±0.28
    ChCh-Miner无注意力的
    原子网络
    95.90±0.99 99.18±0.1596.23±0.34
    本文方法98.45±0.3199.79±0.0496.51±0.84
    下载: 导出CSV

    表  4  分子特征网络的消融实验结果

    Table  4  Ablation experimental results on molecular feature network

    数据集算法AUROCAUPRCF1
    ZhangDDI无注意力的
    分子网络
    98.82±0.2797.18±0.6891.60±1.84
    本文方法99.14±0.0197.97±0.0293.79±0.28
    ChCh-Miner无注意力的
    分子网络
    95.78±1.2999.19±0.3895.19±1.45
    本文方法98.45±0.3199.79±0.0496.51±0.84
    下载: 导出CSV

    表  5  位置编码对模型性能影响的对比结果

    Table  5  Comparison results of the impact of positional encoding on model performance

    数据集算法AUROCAUPRCF1
    ZhangDDI无位置编码98.91±0.2697.46±0.6091.38±2.11
    传统位置编码99.02±0.2197.68±0.5392.70±1.35
    本文方法99.14±0.0197.97±0.0293.79±0.28
    ChCh-Miner无位置编码95.62±2.7999.11±0.6396.12±0.58
    传统位置编码97.54±0.4699.66±0.0694.73±0.54
    本文方法98.45±0.3199.79±0.0496.51±0.84
    下载: 导出CSV

    表  6  损失函数对模型性能影响的对比结果

    Table  6  Comparison results of the impact of loss function on model performance

    数据集算法AUROCAUPRCF1
    ZhangDDI无自蒸馏约束项98.71±0.0196.87±0.0289.53±0.54
    无对比学习损失项94.19±0.0679.62±0.3173.59±0.39
    infoNCE 对比损失项99.10±0.0597.91±0.0992.87±0.60
    不同采样方式的对比损失项99.13±0.0297.97±0.0493.15±0.61
    本文方法99.14±0.0197.97±0.0293.79±0.28
    ChCh-Miner无自蒸馏约束项97.55±3.2499.48±0.8796.34±1.01
    无对比学习损失项58.70±5.0090.30±1.0694.89±0.57
    infoNCE 对比损失项98.59±0.2099.80±0.0397.31±0.20
    不同采样方式的对比损失项98.38±0.0199.78±0.0095.67±0.09
    本文方法98.45±0.3199.79±0.0496.51±0.84
    下载: 导出CSV
  • [1] Ryu J Y, Kim H U, Lee S Y. Deep learning improves prediction of drug-drug and drug-food interactions. The National Academy of Sciences (NAS), 2018, 115(18): E4304−E4311
    [2] Sun M Y, Zhao S D, Gilvary C, Elemento O, Zhou J Y, Wang F. Graph convolutional networks for computational drug development and discovery. Briefings in Bioinformatics, 2020, 21(3): 919-935 doi: 10.1093/bib/bbz042
    [3] Qiu Y, Zhang Y, Deng Y F, Liu S C, Zhang W. A comprehensive review of computational methods for drug-drug interaction detection. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2022, 19(4): 1968−1985
    [4] Abbas K, Abbasi A, Dong Shi, Niu L, Yu L H, Chen B, et al. Application of network link prediction in drug discovery. BMC Bioinformatics, 2021, 22(1): 1-21 doi: 10.1186/s12859-020-03881-z
    [5] 侯美好. 基于图神经网络的药物不良相互作用预测 [硕士学位论文], 山东大学, 中国, 2020.

    Hou Mei-Hao. Prediction of Adverse Drug Interactions Based on Graph Neural Network [Master thesis], Shandong University, China, 2020.
    [6] Lee G, Park C, Ahn J. Novel deep learning model for more accurate prediction of drug-drug interaction effects. BMC Bioinformatics, 2019, 20(1): 1-8 doi: 10.1186/s12859-018-2565-8
    [7] Karim M R, Cochez M, Jares J B, Uddin M, Beyan O, Decker S. Drug-drug interaction prediction based on knowledge graph embeddings and convolutional-lstm network. In: Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics. New York, USA: ACM, 2019. 113−123
    [8] Yan C, Duan G H, Zhang Y Y, Wu F X, Pan Y, Wang J X. IDNDDI: An integrated drug similarity network method for predicting drug-drug interactions. In: Proceedings of the 15th International Symposium on Bioinformatics Research and Applications. Cham, Switzerland: Springer, 2019. 89−99
    [9] Liu S C, Huang Z Y, Qiu Y, Chen Y P P, Zhang W. Structural network embedding using multi-modal deep auto-encoders for predicting drug-drug interactions. In: Proceedings of the IEEE International Conference on Bioinformatics and Biomedicine. San Diego, USA: IEEE, 2019. 445−450
    [10] Deng Y F, Xu X R, Qiu Y, Xia J B, Zhang W, Liu S C. A multimodal deep learning framework for predicting drug–drug interaction events.Bioinformatics, 2020, 36(15): 4316-4322 doi: 10.1093/bioinformatics/btaa501
    [11] Zhang W, Chen Y L, Liu F, Luo F, Tian G, Li X H. Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data.BMC Bioinformatics, 2017, 18(1): 1-12 doi: 10.1186/s12859-016-1414-x
    [12] Ma T F, Xiao C, Zhou J Y, Wang F. Drug similarity integration through attentive multi-view graph auto-encoders. In: Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm, Sweden: Morgan Kaufmann, 2018. 3477−3483
    [13] Wang Y H, Min Y S, Chen X, Wu J. Multi-view graph contrastive representation learning for drug-drug interaction prediction. In: Proceedings of the Web Conference (WWW'21). New York, USA: ACM, 2021. 2921−2933
    [14] Yan C, Duan G H, Zhang Y Y, Wu F X, Pan Y, Wang J X. Predicting drug-drug interactions based on integrated similarity and semi-supervised learning.IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2022, 19(1): 168-179 doi: 10.1109/TCBB.2020.2988018
    [15] Jin B, Yang H Y, Xiao C, Zhang P, Wei X P, Wang F. Multitask dyadic prediction and its application in prediction of adverse drug-drug interaction. In: Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI, 2017. 367−373
    [16] Lin X, Quan Z, Wang Z J, Ma T F, Zeng X X. KGNN: Knowledge graph neural network for drug-drug interaction prediction. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence. Yokohama, Japan: Morgan Kaufmann, 2020. 2739−2745
    [17] Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, et al. Attention is all you need. In: Proceedings of the 30th Annual Conference on Neural Information Processing Systems. Barcelona, Spain: Curran Associates, 2017. 5998−6008
    [18] Chen J W, Zheng S J, Song Y, Rao J H, Yang Y D. Learning attributed graph representations with communicative message passing transformer. In: Proceedings of the 30th International Joint Conference on Artificial Intelligence. Montreal, Canada: Morgan Kaufmann, 2021. 2242−2248
    [19] Landrum G. Rdkit documentation [Online], available: https://www.rdkit.org/, July 29, 2022
    [20] Gilmer J, Schoenholz S S, Riley P F, Vinyals O, Dahl G E. Neural message passing for quantum chemistry. In: Proceedings of the 34th International Conference on Machine Learning. Sydney, Australia: ACM, 2017. 1263−1272
    [21] Zhang L F, Song J B, Gao A, Chen J W, Bao C L, Ma K S. Be your own teacher: Improve the performance of convolutional neural networks via self-distillation. In: Proceedings of the IEEE/CVF International Conference on Computer Vision. Seoul, South Korea: IEEE, 2019. 3713−3722
    [22] Hjelm R D, Fedorov A, Lavoie-Marchildon S, Grewal K, Bachman P, Trischler A, et al. Learning deep representations by mutual information estimation and maximization. In: Proceedings of the 7th International Conference on Learning Representations. New Orleans, USA: OpenReview.net, 2019.
    [23] Zitnik M, Sosic R, Leskovec J. BioSNAP Datasets: Stanford biomedical network dataset collection [Online], available: http://snap.stanford.edu/biodata, July 30, 2022
    [24] Vilar S, Harpaz R, Uriarte E, Santana L, Rabadan R, Friedman C. Drug—drug interaction through molecular structure similarity analysis. Journal of the American Medical Informatics Association, 2012, 19(6): 1066-1074 doi: 10.1136/amiajnl-2012-000935
    [25] Zhang P, Wang F, Hu J Y, Sorrentino R. Label propagation prediction of drug-drug interactions based on clinical side effects. Scientific Reports, 2015, 5(1): 1-10 doi: 10.9734/JSRR/2015/14076
    [26] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks. In: Proceedings of the 5th International Conference on Learning Representations. Toulon, France: OpenReview.net, 2017.
    [27] Xu K Y L, Hu W H, Leskovec J, Jegelka S. How powerful are graph neural networks? In: Proceedings of the 7th International Conference on Learning Representations. New Orleans, USA: OpenReview.net, 2019.
    [28] Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y. Graph attention networks. In: Proceedings of the 6th International Conference on Learning Representations. Montréal, Canada: OpenReview.net, 2018.
    [29] Li J, Rong Y, Cheng H, Meng H L, Huang W B, Huang J Z. Semi-supervised graph classification: A hierarchical graph perspective. In: Proceedings of the World Wide Web Conference. San Francisco, USA: ACM, 2019. 972−982
    [30] Duvenaud D, Maclaurin D, Iparraguirre J, Bombarell R, Hirzel T, Aspuru-Guzik A, et al. Convolutional networks on graphs for learning molecular fingerprints. In: Proceedings of the 28th Annual Conference on Neural Information Processing Systems. Montreal, Canada: MIT, 2015.
  • 加载中
图(6) / 表(6)
计量
  • 文章访问数:  782
  • HTML全文浏览量:  335
  • PDF下载量:  142
  • 被引次数: 0
出版历程
  • 收稿日期:  2022-05-06
  • 录用日期:  2022-07-25
  • 网络出版日期:  2022-11-02
  • 刊出日期:  2023-12-27

目录

    /

    返回文章
    返回